last-checkpoint/trainer_state.json

{
  "best_metric": 1.819774866104126,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.009224383119378891,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030747943731262973,
      "eval_loss": 2.5190646648406982,
      "eval_runtime": 123.6943,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 5.538,
      "step": 1
    },
    {
      "epoch": 0.0009224383119378892,
      "grad_norm": 2.11873459815979,
      "learning_rate": 0.00012,
      "loss": 2.3781,
      "step": 3
    },
    {
      "epoch": 0.0015373971865631486,
      "eval_loss": 2.3793888092041016,
      "eval_runtime": 133.4392,
      "eval_samples_per_second": 10.267,
      "eval_steps_per_second": 5.133,
      "step": 5
    },
    {
      "epoch": 0.0018448766238757784,
      "grad_norm": 1.0229716300964355,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4241,
      "step": 6
    },
    {
      "epoch": 0.0027673149358136673,
      "grad_norm": 0.6360759139060974,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0473,
      "step": 9
    },
    {
      "epoch": 0.0030747943731262973,
      "eval_loss": 2.084104061126709,
      "eval_runtime": 133.8857,
      "eval_samples_per_second": 10.233,
      "eval_steps_per_second": 5.116,
      "step": 10
    },
    {
      "epoch": 0.0036897532477515567,
      "grad_norm": 0.7156891822814941,
      "learning_rate": 0.000163742398974869,
      "loss": 2.0728,
      "step": 12
    },
    {
      "epoch": 0.004612191559689446,
      "grad_norm": 0.8232230544090271,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.801,
      "step": 15
    },
    {
      "epoch": 0.004612191559689446,
      "eval_loss": 1.956713318824768,
      "eval_runtime": 133.571,
      "eval_samples_per_second": 10.257,
      "eval_steps_per_second": 5.128,
      "step": 15
    },
    {
      "epoch": 0.005534629871627335,
      "grad_norm": 0.6906783580780029,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.6975,
      "step": 18
    },
    {
      "epoch": 0.0061495887462525945,
      "eval_loss": 1.865534782409668,
      "eval_runtime": 133.5202,
      "eval_samples_per_second": 10.261,
      "eval_steps_per_second": 5.13,
      "step": 20
    },
    {
      "epoch": 0.0064570681835652245,
      "grad_norm": 1.018054485321045,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.8903,
      "step": 21
    },
    {
      "epoch": 0.0073795064955031135,
      "grad_norm": 0.8236993551254272,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.8529,
      "step": 24
    },
    {
      "epoch": 0.0076869859328157425,
      "eval_loss": 1.8260083198547363,
      "eval_runtime": 133.4963,
      "eval_samples_per_second": 10.262,
      "eval_steps_per_second": 5.131,
      "step": 25
    },
    {
      "epoch": 0.008301944807441002,
      "grad_norm": 0.8157389163970947,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8317,
      "step": 27
    },
    {
      "epoch": 0.009224383119378891,
      "grad_norm": 1.0121748447418213,
      "learning_rate": 0.0,
      "loss": 1.7414,
      "step": 30
    },
    {
      "epoch": 0.009224383119378891,
      "eval_loss": 1.819774866104126,
      "eval_runtime": 133.5545,
      "eval_samples_per_second": 10.258,
      "eval_steps_per_second": 5.129,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4170173481222144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}